Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2105 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3567. Min Range: -7.3567
Max Act: 7.3567. Min Act: -0.1700
Data Index: 4502582 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.8879. Min Act: -0.1700
Data Index: 8064834 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.7629. Min Act: -0.1700
Data Index: 6278980 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.7629. Min Act: -0.1700
Data Index: 1495984 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.7004. Min Act: -0.1700
Data Index: 4094274 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.6379. Min Act: -0.1700
Data Index: 7260780 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.6379. Min Act: -0.1700
Data Index: 8475315 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.6067. Min Act: -0.1700
Data Index: 319095 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.5754. Min Act: -0.1700
Data Index: 955085 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.5129. Min Act: -0.1700
Data Index: 1368740 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.5442. Min Act: -0.1700
Data Index: 7398178 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.4504. Min Act: -0.1700
Data Index: 4502580 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.5129. Min Act: -0.1700
Data Index: 1532032 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.4504. Min Act: -0.1700
Data Index: 4828567 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.4192. Min Act: -0.1700
Data Index: 7874550 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.3879. Min Act: -0.1700
Data Index: 4502581 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.3879. Min Act: -0.1700
Data Index: 4477602 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.3567. Min Act: -0.1700
Data Index: 2003440 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.3567. Min Act: -0.1700
Data Index: 6418572 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3567. Min Range: -7.3567
Max Act: 6.3567. Min Act: -0.1700
Data Index: 6538900 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19